Vector databases · LF AI & Data Foundation (originally Zilliz)
Milvus
Open-source vector database built for billion-scale similarity search, governed under the Linux Foundation.
Milvus is an open-source vector database designed to index and search billions of embeddings with configurable trade-offs between recall, latency and resource use, using multiple ANN index types (HNSW, IVF, DiskANN and others) that can be chosen per collection. It separates storage and compute in its cluster deployment mode, allowing independent scaling of ingestion, indexing and query nodes, and it supports hybrid search combining dense and sparse vectors with scalar filtering. Originally created by Zilliz and later donated to the Linux Foundation's LF AI & Data Foundation, Milvus is self-hosted by default via Docker or Kubernetes (or a lightweight embedded mode, Milvus Lite, for local development). Zilliz continues as the primary corporate contributor and also sells a fully managed cloud version, Zilliz Cloud, built on the same engine.
At a glance
| Vendor | LF AI & Data Foundation (originally Zilliz) |
|---|---|
| Pricing model | Open source + paid options |
| Free tier | Yes |
| Deployment | Self-hosted |
| Open source | Yes (Apache-2.0) |
| Best for | Teams needing self-hosted vector search at very large scale with full control over infrastructure. |
Pricing
Free and open source under the Linux Foundation; a fully managed cloud version is sold separately by Zilliz as Zilliz Cloud.
Pricing has not been verified yet — see the vendor's site.
Features
- Billion-scale approximate nearest-neighbor search
- Multiple ANN index types (HNSW, IVF, DiskANN)
- Hybrid dense + sparse vector search
- Storage-compute separation in cluster mode
- Milvus Lite embedded mode for local development
- Scalar filtering combined with vector search
Integrations
Profile last reviewed September 21, 2026